Task Guided Compositional Representation Learning for ZDA

Abstract

Zero-shot domain adaptation (ZDA) methods aim to transfer knowledge about a task learned in a source domain to a target domain, while data from target domain are not available. In this work, we address learning feature representations which are invariant to and shared among different domains considering task characteristics for ZDA. To this end, we propose a method for task-guided ZDA (TG-ZDA) which employs multi-branch deep neural networks to learn feature representations exploiting their domain invariance and shareability properties. The proposed TG-ZDA models can be trained end-to-end without requiring synthetic tasks and data generated from estimated representations of target domains. The proposed TG-ZDA has been examined using benchmark ZDA tasks on image classification datasets. Experimental results show that our proposed TG-ZDA outperforms state-of-the-art ZDA methods for different domains and tasks.

References in corpus (13)

• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Deep Domain Confusion: Maximizing for Domain Invariance
• Adversarial Discriminative Domain Adaptation
• Understanding the Role of Individual Units in a Deep Neural Network
• Deep CORAL: Correlation Alignment for Deep Domain Adaptation
• Bridging Theory and Algorithm for Domain Adaptation
• Few-Shot Adversarial Domain Adaptation
• On Learning Invariant Representation for Domain Adaptation
• In Search of Lost Domain Generalization
• Support and Invertibility in Domain-Invariant Representations
• Does Invariant Risk Minimization Capture Invariance?
• Adversarial Domain Adaptation with Domain Mixup
• Few-shot Adaptive Faster R-CNN